分析ChatGPT生成诗歌的风格特征，发现其有固定偏好但缺乏人类诗人的多样性。
Does ChatGPT Have a Poetic Style?
- 用24种体裁、40个主题、3种提示模板让GPT-3.5和GPT-4生成5.7千首诗
- 生成诗歌在形式上准确（如十四行诗14行），但语言高度重复且偏好特定词汇
- 适合对AI创作审美或语言模式感兴趣的读者
生成诗歌已成为大模型的重要应用，尤其是广泛使用的OpenAI聊天机器人ChatGPT。ChatGPT究竟像哪位诗人？它是否有独特的诗风？能否成功模仿不同风格？为此，我们向GPT-3.5与GPT-4模型输入24种英语诗体、40个不同主题及3种写作提示模板，生成共5.7千首英文诗，并与来自美国诗歌基金会和美国诗人学院的3.7千首人类诗歌样本进行对比分析。结果表明，GPT模型（尤其是GPT-4）能在多种常见与罕见体裁中以表面恰当的方式生成诗歌，如十四行诗（14行）、芭蕾舞诗（19行）和六节诗（39行）。然而，这些模型也表现出显著的风格倾向：在体裁内外均呈现高度一致性，尤其偏爱押韵、四行诗节、抑扬格节奏、第一人称复数视角（we, us, our）以及特定词汇如'heart'、'embrace'、'echo'、'whisper'。整体来看，GPT诗歌远比人类诗歌更受限制且同质化。
原文摘要 · Abstract (English)
Generating poetry has become a popular application of LLMs, perhaps especially of OpenAI's widely-used chatbot ChatGPT. What kind of poet is ChatGPT? Does ChatGPT have its own poetic style? Can it successfully produce poems in different styles? To answer these questions, we prompt the GPT-3.5 and GPT-4 models to generate English-language poems in 24 different poetic forms and styles, about 40 different subjects, and in response to 3 different writing prompt templates. We then analyze the resulting 5.7k poems, comparing them to a sample of 3.7k poems from the Poetry Foundation and the Academy of American Poets. We find that the GPT models, especially GPT-4, can successfully produce poems in a range of both common and uncommon English-language forms in superficial yet noteworthy ways, such as by producing poems of appropriate lengths for sonnets (14 lines), villanelles (19 lines), and sestinas (39 lines). But the GPT models also exhibit their own distinct stylistic tendencies, both within and outside of these specific forms. Our results show that GPT poetry is much more constrained and uniform than human poetry, showing a strong penchant for rhyme, quatrains (4-line stanzas), iambic meter, first-person plural perspectives (we, us, our), and specific vocabulary like "heart," "embrace," "echo," and "whisper."
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。